Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    asking questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     concerned
    0.73
    We
    0.68
     committing
    0.67
     worried
    0.66
     fortr
    0.65
     adamant
    0.65
     we
    0.65
     expectant
    0.65
    moil
    0.63
     गर्दै
    0.63
    POSITIVE LOGITS
    ioso
    0.75
     کم
    0.74
     هو
    0.71
    IsPass
    0.67
     finns
    0.67
     Gets
    0.66
    گه
    0.66
     Analyzer
    0.65
     recueill
    0.65
    isko
    0.64
    Act Density 0.052%

    No Known Activations